I. Rey-fabret et al., Neural networks tools for improving tacite hydrodynamic simulation of multiphase flow behavior in pipelines, OIL GAS SCI, 56(5), 2001, pp. 471-478
Citations number
8
Categorie Soggetti
Geological Petroleum & Minig Engineering
Journal title
OIL & GAS SCIENCE AND TECHNOLOGY-REVUE DE L INSTITUT FRANCAIS DU PETROLE
Transient multiphase flow simulators are generally used to dimension the pr
oduction scheme. One of the problems encountered is to predict accurately t
he pressure drop and the liquid holdup. This can be solved using an accurat
e numerical scheme and an appropriate thermodynamic behavior linked to an a
ccurate and robust hydrodynamic model. In the Tacite Code, developed by IFP
a mechanistic hydrodynamic model has been developed. This model is able to
predict the flow regime, the phase velocities and the local pressure drop
for all slopes and all diameters. It contains closure laws based on flow re
gimes. This mechanistic model has been validated against various data banks
. The two limitations of such an hydrodynamic model may be its mathematical
disturbance (continuity. derivability are not always guaranteed) and the t
ime consuming. This can be troublesome when using an accurate numerical sch
eme that requires derivative computation and for real time purposes. This p
aper presents a neural network based approach to efficiently replace the hy
drodynamic module in the two phase model with the following two objectives:
- to avoid discontinuity, problems during hydrodynamic computations;
- to reduce significantly computational time.
This method was tested with experimental and simulated data. The results gi
ven in this paper prove the relevancy of this approach.